LongCat 2.0
LongCat 2.0 is a sparse mixture-of-experts language model developed by Meituan. It is designed for complex tasks including coding, repository-level modifications, and long-horizon problem solving.
LongCat 2.0 specs and pricing
- Provider: Meituan
- Released: July 20, 2026
- Context window: 1M tokens
- Max output: 262K tokens
- Input: text
- Output: text
- Price: $0.30 input / $1.20 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What LongCat 2.0 is good at
- Writing and refactoring large codebases
- Solving complex, multi-step problems
- Executing agentic workflows
To-dos to try with LongCat 2.0
- Analyze this entire software repository and suggest refactoring steps to improve modularity
- Plan a multi-step project strategy based on these technical requirements
- Write a script to automate these specific system administration tasks
FAQ
- Who developed LongCat 2.0? LongCat 2.0 was developed by Meituan.
- What is the primary focus of this model? The model is built for coding, repository-level changes, and long-horizon problem solving.
- How much does LongCat 2.0 cost? LongCat 2.0 costs $0.30 per million input tokens and $1.20 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.01 credits ($1 = 100 credits).
- What is the context window of LongCat 2.0? LongCat 2.0 can read up to 1M tokens at once and write up to 262K tokens in one reply.
- Can I use LongCat 2.0 without coding? Yes. In todo.is you pick LongCat 2.0 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.